AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1604 resultsPyTorch NCCL: local DoS in distributed training reduce op
CVE-2025-4287 browser-use: URL allowlist bypass enables SSRF in agents
CVE-2025-47241 LLaMA-Factory: RCE via torch.load() unsafe deserialization
CVE-2025-46567 vLLM: DoS via quadratic multimodal tokenizer input
CVE-2025-46560 vLLM: RCE via pickle deserialization on ZeroMQ
CVE-2025-32444 vLLM: ZeroMQ socket exposure enables DoS in multi-node
CVE-2025-30202 transformers: ReDoS in GPT-NeoX Japanese tokenizer
CVE-2025-1194 n8n: stored XSS enables account takeover
CVE-2025-46343 vLLM: RCE via malicious model, PyTorch < 2.6 bypass
GHSA-ggpf-24jw-3fcw PyTorch: RCE bypasses weights_only=True safe-load guard
CVE-2025-32434 PyTorch: DoS via ctc_loss resource mishandling
CVE-2025-3730 vLLM: DoS via unbounded XGrammar schema cache
GHSA-hf3c-wxg2-49q9 jupyter-remote-desktop-proxy: VNC network exposure
CVE-2025-32428 BentoML: RCE via insecure deserialization in runner
CVE-2025-32375 xgrammar: unbounded grammar cache causes LLM server DoS
CVE-2025-32381 picklescan: bypass allows silent RCE in ML pipelines
GHSA-v7x6-rv5q-mhwc picklescan: numpy bypass enables RCE in ML model pipelines
GHSA-fj43-3qmq-673f picklescan: scanner bypass enables DNS data exfiltration
CVE-2025-46417 Langflow: Unauth RCE via code injection endpoint
CVE-2025-3248 BentoML: unauthenticated RCE via insecure deserialization
CVE-2025-27520 Need deeper analysis?
Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.
Start 14-Day Free Trial
AI Threat Alert